26 citations · 42 across the 5 of their papers we have counts for
5 papers
Attribution Upsampling should Redistribute, Not Interpolate
Vincenzo Buono, Peyman Sheikholharam Mashhadi, Mahmoud Rahat +2
Attribution methods in explainable AI rely on upsampling techniques that were designed for natural images, not saliency maps. Standard bilinear and bicubic interpolation systematic…
Expected Grad-CAM: Towards gradient faithfulness
Vincenzo Buono, Peyman Sheikholharam Mashhadi, Mahmoud Rahat +2
Although input-gradients techniques have evolved to mitigate and tackle the challenges associated with gradients, modern gradient-weighted CAM approaches still rely on vanilla grad…
Rolling the dice for better deep learning performance: A study of randomness techniques in deep neural networks
Mohammed Ghaith Altarabichi, Sławomir Nowaczyk, Sepideh Pashami +2
This paper investigates how various randomization techniques impact Deep Neural Networks (DNNs). Randomization, like weight noise and dropout, aids in reducing overfitting and enha…
Learning Causal Mechanisms through Orthogonal Neural Networks
Peyman Sheikholharam Mashhadi, Slawomir Nowaczyk
A fundamental feature of human intelligence is the ability to infer high-level abstractions from low-level sensory data. An essential component of such inference is the ability to…
Surrogate-Assisted Genetic Algorithm for Wrapper Feature Selection
Mohammed Ghaith Altarabichi, Sławomir Nowaczyk, Sepideh Pashami +1
Feature selection is an intractable problem, therefore practical algorithms often trade off the solution accuracy against the computation time. In this paper, we propose a novel mu…